Metraipolis › archive › dc_dd281f5e45c7

Deep Microcompression: Structured Pruning and Bit-packed Quantization for Microcontrollers — arXiv:2609.05081

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.05081
License (as archived)
CC0-1.0
Archived
2026-10-16T22:58:30.810Z
SHA-256 of the archived text
29ddde43b4834f206e32a2f1d8f030932950ab396a64e7b5282eb1f911c00d77
Stable URL of this page
https://metraipolis.com/documento/dc_dd281f5e45c7

How to cite

Deep Microcompression: Structured Pruning and Bit-packed Quantization for Microcontrollers — arXiv:2609.05081 — arXiv (en), https://arxiv.org/abs/2609.05081 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dd281f5e45c7 (Metraipolis archive dc_dd281f5e45c7, sha256 29ddde43b4834f206e32a2f1d8f030932950ab396a64e7b5282eb1f911c00d77)
BibTeX
@misc{dcdd281f5e45c7,
  title = {Deep Microcompression: Structured Pruning and Bit-packed Quantization for Microcontrollers — arXiv:2609.05081},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.05081},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dd281f5e45c7; sha256 29ddde43b4834f206e32a2f1d8f030932950ab396a64e7b5282eb1f911c00d77},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.05081. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This paper introduces Deep Microcompression (DMC), a hardware-aware pipeline for deep learning inference on bare-metal microcontrollers. DMC integrates structured pruning, quantization-aware training, and fixed-length bit-packing to achieve a 55.8$\times$ weight compression ratio on LeNet-5 (98.77\% accuracy), generating a dependency-free C library with deterministic latency. On the RP2040 (Cortex-M0+), DMC reduces binary size by 3$\times$ versus TensorFlow Lite while matching its accuracy. Critically, DMC enables the first documented deployment of a standard CNN on the ATmega328P, a device constrained to 2KB SRAM, previously considered infeasible for CNN inference.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-07 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.05081 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T22:31:32.204Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).